Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    intend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     homeowner
    -0.07
     messagebox
    -0.06
    .getEmail
    -0.06
    атки
    -0.06
     loung
    -0.06
     Gan
    -0.06
     MutableLiveData
    -0.06
    527
    -0.06
     Dynamics
    -0.06
     nghiệ
    -0.06
    POSITIVE LOGITS
     intended
    0.13
     instructed
    0.08
     unintended
    0.07
    ledon
    0.07
     intending
    0.07
     extended
    0.07
     Desired
    0.07
    ANCED
    0.07
     Quentin
    0.07
    int
    0.07
    Act Density 0.016%

    No Known Activations